Glossary: Application and Credential Attacks, and AI Risks
many-shot prompting
A jailbreak trick that gives a long list of fake examples where an "assistant" answered forbidden questions, nudging the model to continue the pattern.
Glossary: Application and Credential Attacks, and AI Risks
A jailbreak trick that gives a long list of fake examples where an "assistant" answered forbidden questions, nudging the model to continue the pattern.